RAG-GFM: Overcoming In-memory Bottlenecks In Graph Foundation Models Via Retrieval-augmented Generation

Abstract

Graph Foundation Models (GFMs) have emerged as a frontier in graph learning, which are expected to deliver transferable representations across diverse tasks. However, GFMs remain constrained by in-memory bottlenecks: they attempt to encode knowledge into model parameters, which limits semantic capacity, introduces heavy lossy compression with conflicts, and entangles graph representation with the knowledge in ways that hinder efficient adaptation, undermining scalability and interpretability. In this work,we propose RAG-GFM, a Retrieval-Augmented Generation aided Graph Foundation Model that offloads knowledge from parameters and complements parameterized learning. To externalize graph knowledge, we build a dual-modal unified retrieval module, where a semantic store from prefix-structured text and a structural store from centrality-based motif. To preserve heterogeneous information, we design a dual-view alignment objective that contrasts both modalities to capture both content and rela

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyyuan2026rag

Related papers

• MG\(^2\)-RAG: Multi-granularity Graph For Multimodal Retrieval-augmented Generation (2026)0.00
• Erarag: Efficient And Incremental Retrieval Augmented Generation For Growing Corpora (2025)4.51
• Funnelrag: A Coarse-to-fine Progressive Retrieval Paradigm For RAG (2024)3.58
• Optimizing Retrieval-augmented Generation: Analysis Of Hyperparameter Impact On Performance And Efficiency (2025)0.00
• Universalrag: Retrieval-augmented Generation Over Corpora Of Diverse Modalities And Granularities (2025)0.00
• Unigraph2: Learning A Unified Embedding Space To Bind Multimodal Graphs (2025)6.77
• GAAMA: Graph Augmented Associative Memory For Agents (2026)0.00
• Advancing Retrieval-augmented Generation For Structured Enterprise And Internal Data (2025)1.20